Skip to main content
Glama
MCP PostgreSQL Operations

MCP PostgreSQL Operations

by call518

get_async_io_status

Monitor PostgreSQL async I/O subsystem status: view active operations, I/O method, concurrency, and file handle usage. Falls back to configuration info on versions before 18.

Instructions

[Tool Purpose]: Monitor asynchronous I/O subsystem status (PostgreSQL 18+)

[Exact Functionality]:

  • Show active async I/O operations from pg_aios view

  • Display I/O method configuration and concurrency settings

  • Report async I/O file handle usage

  • Falls back to I/O configuration info on PG < 18

[Required Use Cases]:

  • When user requests "async I/O status", "AIO monitoring", "I/O subsystem"

  • When investigating I/O performance and concurrency

  • When checking async I/O configuration

[Strictly Prohibited Use Cases]:

  • Requests for I/O configuration changes

  • Requests for storage modifications

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "get_async_io_status"
  }
}

Input Schema

NameRequiredDescriptionDefault
database_nameNoDatabase name (uses default if omitted)

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv3.4.3
    • addedInput schema / properties / database_name / description
      Added value: +"Database name (uses default if omitted)"
  2. Addedv3.4.2

TDQS

A4.1/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are supplied, so the description carries the full burden; it discloses the key non-obvious behavior — graceful degradation to configuration-only output on PostgreSQL versions below 18 — plus the underlying source view. It never explicitly states that the tool is read-only and side-effect free, though 'Monitor' and 'Show' strongly imply it, and no permission prerequisites are mentioned.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Content is front-loaded and every block earns its place, with the version caveat placed near the top where it matters. The bracketed section headers and bullet scaffolding are somewhat heavier than needed for a one-parameter read tool, but nothing is padded or redundant.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

An output schema exists, so return formatting need not be explained, and the version-fallback behavior plus the enum of covered data make this callable without further reading. The only real omission is read-only/safety framing and any note on how the async-I/O view relates to the other I/O stats tools.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% and the single optional parameter (database_name) is fully documented in the schema, so the baseline of 3 applies. The description adds nothing about database scoping — notably, it does not say whether pg_aios statistics are cluster-wide or per-database when database_name is supplied.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource — monitoring the asynchronous I/O subsystem — and scopes it to PostgreSQL 18+ with a documented fallback. The three bullet points concretely enumerate what is shown (active operations from pg_aios, configuration/concurrency, file handle usage), which is far more than a restatement of the name.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Provides explicit 'Required Use Cases' with quoted trigger phrases and an explicit 'Strictly Prohibited Use Cases' section covering configuration and storage changes. What is missing is sibling differentiation: the toolset contains get_io_stats, get_table_io_stats, get_index_io_stats and get_per_backend_io_stats, and the description never says when to prefer the async-I/O view over those.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.